Lessons from deploying NLG technology for marine weather forecast text generation

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

SUMTIME-MOUSAM is a Natural Language Generation (NLG) system that produces textual weather forecasts for offshore oilrigs from Numerical Weather Prediction (NWT) data. It has been used for the past year by Weathernews (UK) Ltd for producing 150 draft forecasts per day, which are then post-edited by forecasters before being released to end-users. In this paper, we describe how the system works, how it is used at Weathernews and finally some lessons we learnt from building, installing and maintaining SUMTIME-MOUSAM. One important lesson has been that using NLG technology improves maintainability although the biggest maintenance work actually involved changing data formats at the I/O interfaces. We also found our system being used by forecasters in unexpected ways for understanding and editing data. We conclude that the success of a technology owes as much to its functional superiority as to its suitability to the various stakeholders such as developers and users.

Original languageEnglish
Title of host publicationECAI 2004
Subtitle of host publicationProceedings of the 16th Eureopean Conference on Artificial Intelligence
EditorsRamon López de Mántaras, Lorenza Saitta
Place of PublicationAmsterdam, Netherlands
PublisherIOS Press
Pages760-764
Number of pages5
Volume110
ISBN (Print)1586034529, 978-1586034528
Publication statusPublished - 1 Dec 2004
Event16th European Conference on Artificial Intelligence (ECAI 2004) including Prestigious Applicants of Intelligent Systems (PAIS 2004) - Valencia, Spain
Duration: 22 Aug 200427 Aug 2004

Publication series

NameFrontiers in Artificial Intelligence and Applications
PublisherIOS Press
Volume110
ISSN (Print)0922-6389

Conference

Conference16th European Conference on Artificial Intelligence (ECAI 2004) including Prestigious Applicants of Intelligent Systems (PAIS 2004)
CountrySpain
CityValencia
Period22/08/0427/08/04

Cite this

Sripada, G. S., Reiter, E. B., Davy, I., & Nilssen, K. (2004). Lessons from deploying NLG technology for marine weather forecast text generation. In R. L. de Mántaras, & L. Saitta (Eds.), ECAI 2004: Proceedings of the 16th Eureopean Conference on Artificial Intelligence (Vol. 110, pp. 760-764). (Frontiers in Artificial Intelligence and Applications; Vol. 110). Amsterdam, Netherlands: IOS Press.

Lessons from deploying NLG technology for marine weather forecast text generation. / Sripada, Gowri Somayajulu; Reiter, Ehud Baruch; Davy, I ; Nilssen, K .

ECAI 2004: Proceedings of the 16th Eureopean Conference on Artificial Intelligence. ed. / Ramon López de Mántaras; Lorenza Saitta. Vol. 110 Amsterdam, Netherlands : IOS Press, 2004. p. 760-764 (Frontiers in Artificial Intelligence and Applications; Vol. 110).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sripada, GS, Reiter, EB, Davy, I & Nilssen, K 2004, Lessons from deploying NLG technology for marine weather forecast text generation. in RL de Mántaras & L Saitta (eds), ECAI 2004: Proceedings of the 16th Eureopean Conference on Artificial Intelligence. vol. 110, Frontiers in Artificial Intelligence and Applications, vol. 110, IOS Press, Amsterdam, Netherlands, pp. 760-764, 16th European Conference on Artificial Intelligence (ECAI 2004) including Prestigious Applicants of Intelligent Systems (PAIS 2004), Valencia, Spain, 22/08/04.
Sripada GS, Reiter EB, Davy I, Nilssen K. Lessons from deploying NLG technology for marine weather forecast text generation. In de Mántaras RL, Saitta L, editors, ECAI 2004: Proceedings of the 16th Eureopean Conference on Artificial Intelligence. Vol. 110. Amsterdam, Netherlands: IOS Press. 2004. p. 760-764. (Frontiers in Artificial Intelligence and Applications).
Sripada, Gowri Somayajulu ; Reiter, Ehud Baruch ; Davy, I ; Nilssen, K . / Lessons from deploying NLG technology for marine weather forecast text generation. ECAI 2004: Proceedings of the 16th Eureopean Conference on Artificial Intelligence. editor / Ramon López de Mántaras ; Lorenza Saitta. Vol. 110 Amsterdam, Netherlands : IOS Press, 2004. pp. 760-764 (Frontiers in Artificial Intelligence and Applications).
@inproceedings{a187ee6b831a43c789195c3d79a44582,
title = "Lessons from deploying NLG technology for marine weather forecast text generation",
abstract = "SUMTIME-MOUSAM is a Natural Language Generation (NLG) system that produces textual weather forecasts for offshore oilrigs from Numerical Weather Prediction (NWT) data. It has been used for the past year by Weathernews (UK) Ltd for producing 150 draft forecasts per day, which are then post-edited by forecasters before being released to end-users. In this paper, we describe how the system works, how it is used at Weathernews and finally some lessons we learnt from building, installing and maintaining SUMTIME-MOUSAM. One important lesson has been that using NLG technology improves maintainability although the biggest maintenance work actually involved changing data formats at the I/O interfaces. We also found our system being used by forecasters in unexpected ways for understanding and editing data. We conclude that the success of a technology owes as much to its functional superiority as to its suitability to the various stakeholders such as developers and users.",
author = "Sripada, {Gowri Somayajulu} and Reiter, {Ehud Baruch} and I Davy and K Nilssen",
note = "Including Prestigious Applicants of Intelligent Systems, PAIS 2004",
year = "2004",
month = "12",
day = "1",
language = "English",
isbn = "1586034529",
volume = "110",
series = "Frontiers in Artificial Intelligence and Applications",
publisher = "IOS Press",
pages = "760--764",
editor = "{de M{\'a}ntaras}, {Ramon L{\'o}pez} and Lorenza Saitta",
booktitle = "ECAI 2004",

}

TY - GEN

T1 - Lessons from deploying NLG technology for marine weather forecast text generation

AU - Sripada, Gowri Somayajulu

AU - Reiter, Ehud Baruch

AU - Davy, I

AU - Nilssen, K

N1 - Including Prestigious Applicants of Intelligent Systems, PAIS 2004

PY - 2004/12/1

Y1 - 2004/12/1

N2 - SUMTIME-MOUSAM is a Natural Language Generation (NLG) system that produces textual weather forecasts for offshore oilrigs from Numerical Weather Prediction (NWT) data. It has been used for the past year by Weathernews (UK) Ltd for producing 150 draft forecasts per day, which are then post-edited by forecasters before being released to end-users. In this paper, we describe how the system works, how it is used at Weathernews and finally some lessons we learnt from building, installing and maintaining SUMTIME-MOUSAM. One important lesson has been that using NLG technology improves maintainability although the biggest maintenance work actually involved changing data formats at the I/O interfaces. We also found our system being used by forecasters in unexpected ways for understanding and editing data. We conclude that the success of a technology owes as much to its functional superiority as to its suitability to the various stakeholders such as developers and users.

AB - SUMTIME-MOUSAM is a Natural Language Generation (NLG) system that produces textual weather forecasts for offshore oilrigs from Numerical Weather Prediction (NWT) data. It has been used for the past year by Weathernews (UK) Ltd for producing 150 draft forecasts per day, which are then post-edited by forecasters before being released to end-users. In this paper, we describe how the system works, how it is used at Weathernews and finally some lessons we learnt from building, installing and maintaining SUMTIME-MOUSAM. One important lesson has been that using NLG technology improves maintainability although the biggest maintenance work actually involved changing data formats at the I/O interfaces. We also found our system being used by forecasters in unexpected ways for understanding and editing data. We conclude that the success of a technology owes as much to its functional superiority as to its suitability to the various stakeholders such as developers and users.

M3 - Conference contribution

SN - 1586034529

SN - 978-1586034528

VL - 110

T3 - Frontiers in Artificial Intelligence and Applications

SP - 760

EP - 764

BT - ECAI 2004

A2 - de Mántaras, Ramon López

A2 - Saitta, Lorenza

PB - IOS Press

CY - Amsterdam, Netherlands

ER -